Pub Date : 2021-01-21DOI: 10.1109/SAMI50585.2021.9378695
Kevin Ma
In recent times, The “Stay at Home” order has made it a challenge for physical education, especially sports. Tennis players require routine training, but both players and coaches need a new way to continue training while maintaining social distance. This paper proposes a real time machine learning system that enables individual tennis players to have real and independent tennis training without social contact. Our system uses a SensorTile development hardware and embedded workbench software to collect real time sensor data utilizing accelerometers, gyroscopes, and magnetometers. This data can be utilized to detect the motion and orientation of the tennis racket, with this SensorTile system mounted on it. We used several machine learning methods to perform real time tennis swing classification with a variety of tennis players, producing very accurate classification results. Therefore, using this proposed machine learning system, players now have an effective training machine that can tell them if their swings are accurate, eliminating the possibility for human error.
{"title":"A Real Time Artificial Intelligent System for Tennis Swing Classification","authors":"Kevin Ma","doi":"10.1109/SAMI50585.2021.9378695","DOIUrl":"https://doi.org/10.1109/SAMI50585.2021.9378695","url":null,"abstract":"In recent times, The “Stay at Home” order has made it a challenge for physical education, especially sports. Tennis players require routine training, but both players and coaches need a new way to continue training while maintaining social distance. This paper proposes a real time machine learning system that enables individual tennis players to have real and independent tennis training without social contact. Our system uses a SensorTile development hardware and embedded workbench software to collect real time sensor data utilizing accelerometers, gyroscopes, and magnetometers. This data can be utilized to detect the motion and orientation of the tennis racket, with this SensorTile system mounted on it. We used several machine learning methods to perform real time tennis swing classification with a variety of tennis players, producing very accurate classification results. Therefore, using this proposed machine learning system, players now have an effective training machine that can tell them if their swings are accurate, eliminating the possibility for human error.","PeriodicalId":402414,"journal":{"name":"2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127164366","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-21DOI: 10.1109/SAMI50585.2021.9378667
György Györök
The electronic circuits currently in use, the reliability and the life expectancy of the mounted printed circuit boards depend on the quality parameter of the components used, the quality of the production technology and production aids, and the careful product and production planning. With this article, we wish to clarify this heuristic limit, make the aging of the circuit measurable, give an alarm before a critical failure. To this end, we create a microcontroller-supported circuit and control structure that operates cost-effectively, latently, embedded in the circuit. Focusing on hybrid circuits, will be shown the possible method and structure for analog and digital signals. Will be extended our study to an interactive method, in the case of circuit configurations of different sizes.
{"title":"Interactive monitoring of Electronic Circuits with Embedded Microcontroller","authors":"György Györök","doi":"10.1109/SAMI50585.2021.9378667","DOIUrl":"https://doi.org/10.1109/SAMI50585.2021.9378667","url":null,"abstract":"The electronic circuits currently in use, the reliability and the life expectancy of the mounted printed circuit boards depend on the quality parameter of the components used, the quality of the production technology and production aids, and the careful product and production planning. With this article, we wish to clarify this heuristic limit, make the aging of the circuit measurable, give an alarm before a critical failure. To this end, we create a microcontroller-supported circuit and control structure that operates cost-effectively, latently, embedded in the circuit. Focusing on hybrid circuits, will be shown the possible method and structure for analog and digital signals. Will be extended our study to an interactive method, in the case of circuit configurations of different sizes.","PeriodicalId":402414,"journal":{"name":"2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125361880","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-21DOI: 10.1109/SAMI50585.2021.9378697
Norbert Ferenčík, R. Hudák, Viktória Rajťúková, M. Kohan, Tomáš Breškovič, J. Živčák
In this review article, we would like to define the operation and parameterization of processes in devices called bioreactors. A bioreactor is a device that uses the setting of physical processes to influence biological processes. In tissue engineering and biomedical engineering, bioreactors can be used to aid in the development of new tissue in vitro. By providing and altering biochemical or physical regulatory signals, it is possible to induce a state in which the cells will differentiate or form an extracellular matrix prior to implantation. Next, we describe the physical procedures that must be maintained for the proper course of the cell development process in the field of bioreactors. For each cell that is inserted into the bioreactor, there is a predetermined set of parameters that must be observed. In this article, we will focus on the general parameters of bioreactors.
{"title":"Overview Article: Bioreactors Designed for 3D Bioprinted Tissue and Process Parameters","authors":"Norbert Ferenčík, R. Hudák, Viktória Rajťúková, M. Kohan, Tomáš Breškovič, J. Živčák","doi":"10.1109/SAMI50585.2021.9378697","DOIUrl":"https://doi.org/10.1109/SAMI50585.2021.9378697","url":null,"abstract":"In this review article, we would like to define the operation and parameterization of processes in devices called bioreactors. A bioreactor is a device that uses the setting of physical processes to influence biological processes. In tissue engineering and biomedical engineering, bioreactors can be used to aid in the development of new tissue in vitro. By providing and altering biochemical or physical regulatory signals, it is possible to induce a state in which the cells will differentiate or form an extracellular matrix prior to implantation. Next, we describe the physical procedures that must be maintained for the proper course of the cell development process in the field of bioreactors. For each cell that is inserted into the bioreactor, there is a predetermined set of parameters that must be observed. In this article, we will focus on the general parameters of bioreactors.","PeriodicalId":402414,"journal":{"name":"2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131133590","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-21DOI: 10.1109/SAMI50585.2021.9378648
Ogbolu Melvin Omone, L. Kovács, M. Kozlovszky
Statistics is defined as the combination of numerous mathematical methods and logic models that are used for appropriate decisions making or judgments that involves uncertainty. However, the expected result could be certain/uncertain. Hence, it can be applied in many areas of life, which includes problem-solving purposes, investigations, and for making scientific conclusions. In biomedicine, the study of statistics is known as biostatistics. It involves the applications of control methods and pathophysiological modeling for data interpretation and presentation. This paper reveals the concept of data analysis as related to biostatistics and its methods which are useful for Statisticians with the use of R programming language. When raw data cannot be interpreted, it is then processed using fundamental statistical tools/methods. Therefore, this paper highlights the statistical methods that are required for a well-processed data and how the methods are applied. The purpose of this paper is to prove the ability to choose the statistical method and test which is suitable for a specific investigation, how to apply the test, and interpret the results using tables and graphs.
{"title":"The Basic Application of Biostatistics to Biomedical Science Using R Programming","authors":"Ogbolu Melvin Omone, L. Kovács, M. Kozlovszky","doi":"10.1109/SAMI50585.2021.9378648","DOIUrl":"https://doi.org/10.1109/SAMI50585.2021.9378648","url":null,"abstract":"Statistics is defined as the combination of numerous mathematical methods and logic models that are used for appropriate decisions making or judgments that involves uncertainty. However, the expected result could be certain/uncertain. Hence, it can be applied in many areas of life, which includes problem-solving purposes, investigations, and for making scientific conclusions. In biomedicine, the study of statistics is known as biostatistics. It involves the applications of control methods and pathophysiological modeling for data interpretation and presentation. This paper reveals the concept of data analysis as related to biostatistics and its methods which are useful for Statisticians with the use of R programming language. When raw data cannot be interpreted, it is then processed using fundamental statistical tools/methods. Therefore, this paper highlights the statistical methods that are required for a well-processed data and how the methods are applied. The purpose of this paper is to prove the ability to choose the statistical method and test which is suitable for a specific investigation, how to apply the test, and interpret the results using tables and graphs.","PeriodicalId":402414,"journal":{"name":"2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129000492","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-21DOI: 10.1109/SAMI50585.2021.9378621
Maryam Khanian Najafabadi, M. Nair, A. Mohamed
Tag recommendation models serve as extracting metadata for target objects like images, videos and Web pages. However, these models tackle cold start problem due to absence of initial tags. To improve tag quality in tag recommendation services, most of previous works exploit the statistical properties such as co-occurrence patterns or term frequency to predict the candidate tags to a target object. Yet, these tag recommendation methods fail to be effective when initial tags are absent or low quality texts are available for objects. Recently, sentence modeling via word embeddings achieves successes in many natural language processing tasks. Therefore, this paper aims to introduce a novel tag recommendation algorithm that can analyze the relation between words in a text associated with target object using word embedding. In fact, we involve grammatical relations between words in a text or sentence with focus on feature learning methods. Skip-gram model is used to optimize feature values and learn the representation vector of words for tag recommendation. Our method shows improvements to previous research methods with gains of up to 10 percent in precision using real data from Movielens dataset.
{"title":"Tag recommendation model using feature learning via word embedding","authors":"Maryam Khanian Najafabadi, M. Nair, A. Mohamed","doi":"10.1109/SAMI50585.2021.9378621","DOIUrl":"https://doi.org/10.1109/SAMI50585.2021.9378621","url":null,"abstract":"Tag recommendation models serve as extracting metadata for target objects like images, videos and Web pages. However, these models tackle cold start problem due to absence of initial tags. To improve tag quality in tag recommendation services, most of previous works exploit the statistical properties such as co-occurrence patterns or term frequency to predict the candidate tags to a target object. Yet, these tag recommendation methods fail to be effective when initial tags are absent or low quality texts are available for objects. Recently, sentence modeling via word embeddings achieves successes in many natural language processing tasks. Therefore, this paper aims to introduce a novel tag recommendation algorithm that can analyze the relation between words in a text associated with target object using word embedding. In fact, we involve grammatical relations between words in a text or sentence with focus on feature learning methods. Skip-gram model is used to optimize feature values and learn the representation vector of words for tag recommendation. Our method shows improvements to previous research methods with gains of up to 10 percent in precision using real data from Movielens dataset.","PeriodicalId":402414,"journal":{"name":"2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI)","volume":"285 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127397547","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-21DOI: 10.1109/SAMI50585.2021.9378687
K. Doki, Kenya Suzuki, A. Torii, S. Mototani, Yuki Funabora, S. Doki
In this paper, we propose a new teleoperation system of a mobile robot using Augmented Reality(AR) based on 3D LiDAR information for operator support. In the proposed system, an 360-degree camera is equipped with a robot which works in a remote place controlled by an operator, and the captured 360-degree image is displayed to the head mounted display put on the head of the operator. The operator can smoothly control the robot watching what he needs for his task by turning his head. In addition, the provided image around the robot has no blind spot because of the 360-degree image. However, the data size of the 360-degree image is enormous and it causes a large transfer delay or dropped frames which adversely influence the operator performance. In order to solve this problem, it is proposed that an AR image is actually provided to the operator, in which objects generated based on 3D LiDAR information are superimposed on the 360-degree image as AR objects. In this paper, the usefulness of the proposed method is shown through the experimental results on parking the robot remotely.
{"title":"AR video presentation using 3D LiDAR information for operator support in mobile robot teleoperation","authors":"K. Doki, Kenya Suzuki, A. Torii, S. Mototani, Yuki Funabora, S. Doki","doi":"10.1109/SAMI50585.2021.9378687","DOIUrl":"https://doi.org/10.1109/SAMI50585.2021.9378687","url":null,"abstract":"In this paper, we propose a new teleoperation system of a mobile robot using Augmented Reality(AR) based on 3D LiDAR information for operator support. In the proposed system, an 360-degree camera is equipped with a robot which works in a remote place controlled by an operator, and the captured 360-degree image is displayed to the head mounted display put on the head of the operator. The operator can smoothly control the robot watching what he needs for his task by turning his head. In addition, the provided image around the robot has no blind spot because of the 360-degree image. However, the data size of the 360-degree image is enormous and it causes a large transfer delay or dropped frames which adversely influence the operator performance. In order to solve this problem, it is proposed that an AR image is actually provided to the operator, in which objects generated based on 3D LiDAR information are superimposed on the 360-degree image as AR objects. In this paper, the usefulness of the proposed method is shown through the experimental results on parking the robot remotely.","PeriodicalId":402414,"journal":{"name":"2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128443724","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-21DOI: 10.1109/SAMI50585.2021.9378634
Ivan Cík, Andrinandrasana David Rasamoelina, M. Mach, P. Sinčák
Artificial intelligence is the mainstream solution to various problems, and thanks to developments in hardware, it is possible to achieve performance like never before. Continuous data collection provides us with opportunities for the creation of various datasets, which are the basis for various challenges. One of those challenges is recognizing emotions from humans' facial expressions. Multiple deep learning models exist in the wild to solve such a task. They always yield high accuracy on their respective validation and test set. However, the performance of such a model tends to decrease when used on real-world images. This work gives insight into how such a deep learning model can predict facial expression from biases present in training data.
{"title":"What makes a smile? A Deep Neural Network Point of View","authors":"Ivan Cík, Andrinandrasana David Rasamoelina, M. Mach, P. Sinčák","doi":"10.1109/SAMI50585.2021.9378634","DOIUrl":"https://doi.org/10.1109/SAMI50585.2021.9378634","url":null,"abstract":"Artificial intelligence is the mainstream solution to various problems, and thanks to developments in hardware, it is possible to achieve performance like never before. Continuous data collection provides us with opportunities for the creation of various datasets, which are the basis for various challenges. One of those challenges is recognizing emotions from humans' facial expressions. Multiple deep learning models exist in the wild to solve such a task. They always yield high accuracy on their respective validation and test set. However, the performance of such a model tends to decrease when used on real-world images. This work gives insight into how such a deep learning model can predict facial expression from biases present in training data.","PeriodicalId":402414,"journal":{"name":"2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128917018","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-21DOI: 10.1109/SAMI50585.2021.9378631
Z. Varga, Ervin Rácz
A great deal of acts have been done for the renewable and green energy to fulfil the global energy demand. The European Union has been working on reducing the carbon-dioxide emission and increasing the available renewable sources of energy. It seems that solar energy is a forward-looking option. According to Michael Grätzel, Dye Sensitized Solar Cell will be a breakthrough concept for energy demand. Although renewable energy is not a fully new concept nowadays, there is a continuous improvment in this field. This article illustrates the maximum power point of an unknown Dye Sensitized Solar Cell (whose inventor is Michael Crätzel) based on cell temperature and using different color filter films.
{"title":"Influence of the Cell Temperature on the Performance of a Dye Sensitized Solar Cell","authors":"Z. Varga, Ervin Rácz","doi":"10.1109/SAMI50585.2021.9378631","DOIUrl":"https://doi.org/10.1109/SAMI50585.2021.9378631","url":null,"abstract":"A great deal of acts have been done for the renewable and green energy to fulfil the global energy demand. The European Union has been working on reducing the carbon-dioxide emission and increasing the available renewable sources of energy. It seems that solar energy is a forward-looking option. According to Michael Grätzel, Dye Sensitized Solar Cell will be a breakthrough concept for energy demand. Although renewable energy is not a fully new concept nowadays, there is a continuous improvment in this field. This article illustrates the maximum power point of an unknown Dye Sensitized Solar Cell (whose inventor is Michael Crätzel) based on cell temperature and using different color filter films.","PeriodicalId":402414,"journal":{"name":"2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132292457","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-21DOI: 10.1109/SAMI50585.2021.9378636
Tolgay Balci, H. Oğul
Measuring the performance and profitability of the banking sector, which is the most important part of a country's financial system, is always important. Thanks to the performance measurement, banks can understand the competitive situation, their potential to grow, and the risk, and be more successful in sustaining their lives. This study is considered all state deposit money banks in Turkey. In the literature, using of artificial neural networks (ANN) in banking performance evaluation is rarely studied. Therefore, this paper aims to examine the possibility of ANN utilization for predicting return on equity of Turkey State Deposit Money Banks. The paper compares the accuracy percentages of optimization algorithms of ANN using eleven years quarterly data of six exogenous variables and eight endogenous variables as independent variables and the average return on equity from quarterly of all Turkey state deposit money banks as dependent variable. Given a number of recorded financial parameters, the task is to predict banks' performances using ANN computation methods and to compare prediction results with real results. To evaluate these methods, we built a data set from Banking Regulation and Supervison of Agency, The Banks Association of Turkey and banks' quarterly financial reports. According to all experimental results in optimization models were estimated with above % 80 accuracy. It is determined that the best optimization model is different for each bank.
{"title":"Predicting Bank Return on Equity (ROE) using Neural Networks","authors":"Tolgay Balci, H. Oğul","doi":"10.1109/SAMI50585.2021.9378636","DOIUrl":"https://doi.org/10.1109/SAMI50585.2021.9378636","url":null,"abstract":"Measuring the performance and profitability of the banking sector, which is the most important part of a country's financial system, is always important. Thanks to the performance measurement, banks can understand the competitive situation, their potential to grow, and the risk, and be more successful in sustaining their lives. This study is considered all state deposit money banks in Turkey. In the literature, using of artificial neural networks (ANN) in banking performance evaluation is rarely studied. Therefore, this paper aims to examine the possibility of ANN utilization for predicting return on equity of Turkey State Deposit Money Banks. The paper compares the accuracy percentages of optimization algorithms of ANN using eleven years quarterly data of six exogenous variables and eight endogenous variables as independent variables and the average return on equity from quarterly of all Turkey state deposit money banks as dependent variable. Given a number of recorded financial parameters, the task is to predict banks' performances using ANN computation methods and to compare prediction results with real results. To evaluate these methods, we built a data set from Banking Regulation and Supervison of Agency, The Banks Association of Turkey and banks' quarterly financial reports. According to all experimental results in optimization models were estimated with above % 80 accuracy. It is determined that the best optimization model is different for each bank.","PeriodicalId":402414,"journal":{"name":"2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131789546","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：